Borrowing it
Nothing to install: this file belongs to liuqiaodongdong/gleaner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liuqiaodongdong/gleaner/main/AGENTS.mdgit clone --depth 1 https://github.com/liuqiaodongdong/gleanerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/liuqiaodongdong/gleaner/agents-md)<a href="https://agentmods.dev/instructions/liuqiaodongdong/gleaner/agents-md"><img src="https://agentmods.dev/badge/instructions/liuqiaodongdong/gleaner/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/liuqiaodongdong/gleaner/agents-md"><img src="https://agentmods.dev/badge/instructions/liuqiaodongdong/gleaner/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02415 | $0.02415 |
| Opus 5.5 | $0.00966 | $0.00966 |
| Sonnet 5.5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
gleaner AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 使用约定（Gleaner Skill + CLI）
你正在使用 gleaner 学术文献采集能力。入口是 Skill + gleaner_cli.py。
装机（仓库 ↔ Skill，必须成对）
用户说「安装项目 / clone」或「安装 skill / 注册 skill / 安装这个 skill」时，没有 gleaner_cli.py 就必须先 clone。只拷 SKILL.md 不算装完。
- 本机没有
gleaner_cli.py（安装 skill 也走这一步）：
git clone https://github.com/liuqiaodongdong/gleaner.git→pip install -r requirements.txt - 在仓库根：
python gleaner_cli.py install-skill
会拷到~/.grok/skills/gleaner、~/.cursor/skills/gleaner、~/.codex/skills/gleaner，并写入.gleaner_root。 - 当前会话设
GLEANER_ROOT为仓库绝对路径。 - 再
status；知网无 cookie 则 Agent 自己跑login.py（脚本内超级鹰自动过滑块）。仅首次加ACQ_ALLOW_COLD_LOGIN=1。不要只跑login-hint，不要让用户手拖。
根目录与 Skill
| 项 | 说明 |
|---|---|
| 默认仓库根 | 见 GLEANER_ROOT；未设时用 gleaner_cli.py 所在仓库根或 CLI --root |
| 环境变量 | GLEANER_ROOT 指向本仓库根（含 gleaner_cli.py） |
| 用户 Skill | 仓库 skill/gleaner/；用 install-skill 注册到 ~/.grok / ~/.cursor / ~/.codex |
| 凭据 | 优先进程环境 / GLEANER_ROOT/.env；Elsevier 也可 acq/data/.elsevier_key |
$env:GLEANER_ROOT = "<本仓库绝对路径>"
python "$env:GLEANER_ROOT\gleaner_cli.py" status
# 或
pwsh "$env:USERPROFILE\.grok\skills\gleaner\scripts\gleaner.ps1" status
首次 / 采集前：必须做部署引导
- 先跑
python gleaner_cli.py status（不要先假设用户已配好密钥）。 - 阅读返回的
lines.*.ready、blockers、next_steps_for_user。 - 若用户要用的线
ready=false：- 用清晰清单展示给用户（申请网址、要填哪些环境变量、本地命令）。
- 协助用户完成配置（写
GLEANER_ROOT/.env、写acq/data/.elsevier_key）。 - 知网必须先有
cookies.json：没有则 Agent 自己启动login.py（有头 Edge，脚本内超级鹰自动过滑块并写盘）。禁止只打印login-hint、禁止让用户手拖或复制 cookie。仅首次加ACQ_ALLOW_COLD_LOGIN=1。禁止无 cookie 就跑cnki/cnki-list（冷启动下不了全文，只会空烧超级鹰）。 - 不要在未就绪时强行跑
cnki/els（CLI 会返回setup_incomplete）。
- 用户表示已配置后，再跑一次
status确认，再开始采集。
各线需要什么
| 线 | CLI 子命令 | 硬门槛 | 推荐 |
|---|---|---|---|
| CNKI 全文 | cnki |
机构代理 + 超级鹰 + cookies.json |
首次 ACQ_ALLOW_COLD_LOGIN=1 录 cookie；之后热启动 |
| CNKI 题录 | cnki-list |
机构代理 + cookies.json |
同上，无 cookie 不准开浏览器 |
| CNKI 分级建式 | prepare |
无（纯本地、不启浏览器） | Agent 先做关键词拓展 |
| Elsevier | els |
官方 ELSEVIER_API_KEY 或 acq/data/.elsevier_key |
见下方官方申请流程 |
| 注册 Skill | install-skill |
仓库内有 skill/gleaner/SKILL.md |
clone + pip 之后立刻跑 |
| 就绪检查 | status |
— | 每次采集前 |
| 源摘要 | sources |
— | 可选 |
| 超级鹰积分 | score |
CJY_* |
排障 |
| 登录提示 | login-hint |
— | 首次装机必做；之后 cookie 过期再跑 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · -1 lines · +20 tokens per session ba9b36f87405
- 1mo ago Changed · +14 lines · +451 tokens per session 82c342c1cb9f
- 1mo ago First seen · 114 lines · 1,944 tokens per session scan A fc9b44927cff
gleaner AGENTS.md is an instructions file published in the GitHub repository liuqiaodongdong/gleaner (3 stars, last pushed 5d ago), licensed MIT. It adds 2,415 tokens to every session, about $0.0097 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.